import os
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Rescaling, Conv2D, MaxPooling2D, Dense, Flatten, Dropout, BatchNormalization
from tensorflow.keras.preprocessing.image import ImageDataGenerator
from tensorflow.keras.optimizers import Adam
from sklearn.metrics import confusion_matrix, precision_score, recall_score, accuracy_score, f1_score
# location path of the datasets
train_dir = "/Users/preslav/Downloads/cw_cop528/imageset/train"
test_dir = "/Users/preslav/Downloads/cw_cop528/imageset/val"
# setting a common standard for the pixel values, to fall in
# setting a validation and training split, alongside augmentation
# details about the train dataset
train_data = ImageDataGenerator(rescale=1./255,
rotation_range=40,
shear_range=0.2,
zoom_range=0.3,
horizontal_flip=True,
fill_mode="nearest",
width_shift_range=0.3,
height_shift_range=0.3,
validation_split=0.2)
val_data = ImageDataGenerator(rescale=1/255,
validation_split=0.2)
test_data = ImageDataGenerator(rescale=1./255)
# importing the data batches and setting their properties
train_batches = train_data.flow_from_directory(directory = train_dir,
target_size = (224, 224),
subset = "training",
batch_size = 32,
seed = 2)
validation_batches = val_data.flow_from_directory(directory = train_dir,
target_size = (224, 224),
subset = "validation",
batch_size = 32,
seed = 2)
test_batches = test_data.flow_from_directory(directory = test_dir,
target_size = (224, 224),
batch_size = 32,
shuffle = False)
Found 7578 images belonging to 10 classes. Found 1891 images belonging to 10 classes. Found 3925 images belonging to 10 classes.
# import of the class labels names and their total number
class_names = list(train_batches.class_indices.keys())
num_classes = len(class_names)
print(class_names)
print(num_classes)
['building', 'dog', 'fish', 'gas_station', 'golf', 'musician', 'parachute', 'radio', 'saw', 'vehicle'] 10
# importing a batch of images and labels
img, lbl = next(train_batches)
# plotting 9 images and their respective class labels
plt.figure(figsize = (12, 12))
for i in range(9):
class_index = np.argmax(lbl[i])
plt.subplot(3, 3, i + 1)
plt.imshow(img[i])
plt.title(class_names[class_index])
plt.axis("off")
plt.tight_layout()
plt.show()
# setting the model's architecture
model_augmented = Sequential([
Conv2D(16, (3,3), 1, activation = "relu"),
MaxPooling2D(),
Conv2D(32, (3,3), 1, activation = "relu"),
Conv2D(32, (3,3), 1, activation = "relu"),
MaxPooling2D(),
Conv2D(32, (3,3), 1, activation = "relu"),
Conv2D(32, (3,3), 1, activation = "relu"),
MaxPooling2D(),
Flatten(),
Dense(256, activation = "relu"),
Dense(num_classes, activation = "softmax")
])
Metal device set to: Apple M2
2023-03-17 11:25:11.992845: I tensorflow/core/common_runtime/pluggable_device/pluggable_device_factory.cc:305] Could not identify NUMA node of platform GPU ID 0, defaulting to 0. Your kernel may not have been built with NUMA support. 2023-03-17 11:25:11.992949: I tensorflow/core/common_runtime/pluggable_device/pluggable_device_factory.cc:271] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 0 MB memory) -> physical PluggableDevice (device: 0, name: METAL, pci bus id: <undefined>)
# setting the model's loss function, gradient descnet optimizer and evaluation metrics
model_augmented.compile(optimizer = "adam", loss = "categorical_crossentropy", metrics = ["accuracy"])
# performing training of the model with the training batches and validaiton batches
epochs = 20
history_augmented= model_augmented.fit(train_batches,
validation_data = validation_batches,
epochs = epochs)
Epoch 1/20
2023-03-17 11:25:12.523623: W tensorflow/core/platform/profile_utils/cpu_utils.cc:128] Failed to get CPU frequency: 0 Hz 2023-03-17 11:25:12.806194: I tensorflow/core/grappler/optimizers/custom_graph_optimizer_registry.cc:113] Plugin optimizer for device_type GPU is enabled.
237/237 [==============================] - ETA: 0s - loss: 2.1250 - accuracy: 0.2292
2023-03-17 11:25:59.261994: I tensorflow/core/grappler/optimizers/custom_graph_optimizer_registry.cc:113] Plugin optimizer for device_type GPU is enabled.
237/237 [==============================] - 50s 210ms/step - loss: 2.1250 - accuracy: 0.2292 - val_loss: 1.8182 - val_accuracy: 0.3406 Epoch 2/20 237/237 [==============================] - 50s 211ms/step - loss: 1.8170 - accuracy: 0.3638 - val_loss: 2.0248 - val_accuracy: 0.3670 Epoch 3/20 237/237 [==============================] - 50s 209ms/step - loss: 1.6995 - accuracy: 0.4045 - val_loss: 1.6463 - val_accuracy: 0.4320 Epoch 4/20 237/237 [==============================] - 50s 209ms/step - loss: 1.6431 - accuracy: 0.4322 - val_loss: 1.5727 - val_accuracy: 0.4691 Epoch 5/20 237/237 [==============================] - 50s 210ms/step - loss: 1.5672 - accuracy: 0.4609 - val_loss: 1.5256 - val_accuracy: 0.4944 Epoch 6/20 237/237 [==============================] - 50s 210ms/step - loss: 1.4737 - accuracy: 0.5022 - val_loss: 1.4293 - val_accuracy: 0.5272 Epoch 7/20 237/237 [==============================] - 49s 208ms/step - loss: 1.4653 - accuracy: 0.5020 - val_loss: 1.4503 - val_accuracy: 0.5256 Epoch 8/20 237/237 [==============================] - 50s 210ms/step - loss: 1.4199 - accuracy: 0.5158 - val_loss: 1.4762 - val_accuracy: 0.5098 Epoch 9/20 237/237 [==============================] - 50s 209ms/step - loss: 1.3802 - accuracy: 0.5376 - val_loss: 1.3611 - val_accuracy: 0.5537 Epoch 10/20 237/237 [==============================] - 50s 210ms/step - loss: 1.3417 - accuracy: 0.5554 - val_loss: 1.3528 - val_accuracy: 0.5568 Epoch 11/20 237/237 [==============================] - 50s 209ms/step - loss: 1.3090 - accuracy: 0.5657 - val_loss: 1.3023 - val_accuracy: 0.5701 Epoch 12/20 237/237 [==============================] - 50s 209ms/step - loss: 1.2693 - accuracy: 0.5760 - val_loss: 1.1719 - val_accuracy: 0.6192 Epoch 13/20 237/237 [==============================] - 50s 209ms/step - loss: 1.2389 - accuracy: 0.5839 - val_loss: 1.1137 - val_accuracy: 0.6335 Epoch 14/20 237/237 [==============================] - 50s 209ms/step - loss: 1.2220 - accuracy: 0.5911 - val_loss: 1.1868 - val_accuracy: 0.6177 Epoch 15/20 237/237 [==============================] - 50s 209ms/step - loss: 1.2137 - accuracy: 0.5912 - val_loss: 1.1256 - val_accuracy: 0.6177 Epoch 16/20 237/237 [==============================] - 50s 209ms/step - loss: 1.1934 - accuracy: 0.6016 - val_loss: 1.2430 - val_accuracy: 0.6118 Epoch 17/20 237/237 [==============================] - 50s 210ms/step - loss: 1.1758 - accuracy: 0.6077 - val_loss: 1.1372 - val_accuracy: 0.6383 Epoch 18/20 237/237 [==============================] - 50s 210ms/step - loss: 1.1381 - accuracy: 0.6145 - val_loss: 1.1034 - val_accuracy: 0.6489 Epoch 19/20 237/237 [==============================] - 50s 209ms/step - loss: 1.1223 - accuracy: 0.6355 - val_loss: 1.0963 - val_accuracy: 0.6372 Epoch 20/20 237/237 [==============================] - 50s 209ms/step - loss: 1.1240 - accuracy: 0.6309 - val_loss: 1.0692 - val_accuracy: 0.6515
# getting model's summary
model_augmented.summary()
Model: "sequential"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
conv2d (Conv2D) (None, None, None, 16) 448
max_pooling2d (MaxPooling2D (None, None, None, 16) 0
)
conv2d_1 (Conv2D) (None, None, None, 32) 4640
conv2d_2 (Conv2D) (None, None, None, 32) 9248
max_pooling2d_1 (MaxPooling (None, None, None, 32) 0
2D)
conv2d_3 (Conv2D) (None, None, None, 32) 9248
conv2d_4 (Conv2D) (None, None, None, 32) 9248
max_pooling2d_2 (MaxPooling (None, None, None, 32) 0
2D)
flatten (Flatten) (None, None) 0
dense (Dense) (None, 256) 4718848
dense_1 (Dense) (None, 10) 2570
=================================================================
Total params: 4,754,250
Trainable params: 4,754,250
Non-trainable params: 0
_________________________________________________________________
# Graphical evaluation of training performance
acc = history_augmented.history['accuracy']
val_acc = history_augmented.history['val_accuracy']
loss = history_augmented.history['loss']
val_loss = history_augmented.history['val_loss']
epochs_range = range(epochs)
plt.figure(figsize=(11, 8))
plt.subplots_adjust(hspace = .3)
plt.subplot(2, 1, 1)
plt.plot(epochs_range, acc, label = 'Training Accuracy', color = "orange")
plt.plot(epochs_range, val_acc, label = 'Validation Accuracy', color = "blue")
plt.legend(loc = 'best')
plt.xlabel('Epochs')
plt.title('Training and Validation Accuracy', size = 13)
plt.subplot(2, 1, 2)
plt.plot(epochs_range, loss, label = 'Training Loss', color = "orange")
plt.plot(epochs_range, val_loss, label = 'Validation Loss', color = "blue")
plt.legend(loc = 'best')
plt.title('Training and Validation Loss', size = 13)
plt.xlabel('Epochs')
plt.suptitle("Base Model with Data Augmentation", size=15)
plt.show()
# Test loss and accuracy measurments
test_loss, test_acc = model_augmented.evaluate(test_batches)
print('Test loss:', test_loss)
print('Test accuracy:', test_acc)
123/123 [==============================] - 7s 57ms/step - loss: 1.0504 - accuracy: 0.6642 Test loss: 1.0504111051559448 Test accuracy: 0.6642038822174072
# getting prediction labales by running the softmax results in argmax
test_labels = test_batches.classes
y_pred = model_augmented.predict(test_batches)
predicted_lables = np.argmax(y_pred, axis = 1)
cm = confusion_matrix(test_labels, predicted_lables)
2/123 [..............................] - ETA: 7s
2023-03-17 11:41:54.307492: I tensorflow/core/grappler/optimizers/custom_graph_optimizer_registry.cc:113] Plugin optimizer for device_type GPU is enabled.
123/123 [==============================] - 7s 56ms/step
# dataframe containing the confussion matrix
cfm = pd.DataFrame(cm, index = class_names, columns = class_names)
# plotting the conffusion matrix
sns.heatmap(cfm, annot=True, fmt='d', cmap='Purples')
plt.xlabel('Predicted Label')
plt.ylabel('True Label')
plt.xticks(rotation=78)
plt.title('Base Model with Augmentation', size = 15)
plt.show()
print("Preicision score:", precision_score(test_labels, predicted_lables, average="weighted"))
print("Recall score:", recall_score(test_labels, predicted_lables, average = "weighted"))
print("F1_score:", f1_score(test_labels, predicted_lables, average = "weighted"))
Preicision score: 0.6947771548506045 Recall score: 0.664203821656051 F1_score: 0.6675302072358554
# importing the test datest again, so that this time images can be shuffled
# so that displayed images are not ordered in the same way as in the dataset
# and variety of classes can be examined
test_data_shuffled = tf.keras.utils.image_dataset_from_directory(test_dir, shuffle = True, seed = 247)
Found 3925 files belonging to 10 classes.
def right_format_image(pic):
'''
This function returns a
reshaped image into 224x224
format in terms of height and
width.
Further it normalizes the
pixel values within the range
of [0, 1].
'''
img_size = (224, 224)
image = tf.image.resize(pic, img_size)
image_expanded = np.expand_dims(image, axis=0)
image_copy = np.copy(image_expanded)
normalized = image_copy/255.
return normalized
def data_iterator(data):
'''
This function returns as arrays the
components of a batch.
'''
iterator = data.as_numpy_iterator()
batch = iterator.next()
return batch
# plotting images from the test dataset, with their actual and predicted from the model labels
predicted_batch = data_iterator(test_data_shuffled)
plt.figure(figsize=(12, 12))
plt.subplots_adjust(hspace = .1, wspace=.3)
plt.suptitle("Base Model with Data Augmentation", size = 20)
for i in range(9):
image, label = predicted_batch[0][i], predicted_batch[1][i]
predictions = model_augmented.predict(right_format_image(image))
prediction_label = class_names[predictions.argmax()]
ax = plt.subplot(3, 3, i + 1)
plt.imshow(image.astype(np.uint8))
plt.title("Actual label:{};\nPredicted label:{}".format(class_names[label],
class_names[predictions.argmax()]), size = 9)
plt.axis("off")
1/1 [==============================] - 0s 66ms/step 1/1 [==============================] - 0s 7ms/step 1/1 [==============================] - 0s 7ms/step 1/1 [==============================] - 0s 7ms/step 1/1 [==============================] - 0s 7ms/step 1/1 [==============================] - 0s 7ms/step
2023-03-17 11:42:01.807644: I tensorflow/core/grappler/optimizers/custom_graph_optimizer_registry.cc:113] Plugin optimizer for device_type GPU is enabled.
1/1 [==============================] - 0s 7ms/step 1/1 [==============================] - 0s 7ms/step 1/1 [==============================] - 0s 8ms/step